cf7-spam-to-telegram/tests/ClassifierTest.php

<?php
declare(strict_types=1);

namespace Cf7stg\Tests;

use Cf7stg\Classifier;

final class ClassifierTest extends Cf7stgTestCase
{
    public function test_real_client_inquiry_is_green(): void
    {
        $fields = [
            'your-name'    => 'Анна Петровна',
            'your-tel'     => '+7 903 123-45-67',
            'your-email'   => 'anna@mail.ru',
            'your-message' => 'Нужна сиделка для бабушки после инсульта, пожалуйста перезвоните.',
        ];
        $r = Classifier::classify($fields, ['reason' => 'Akismet']);
        self::assertSame('client', $r['label']);
        self::assertGreaterThanOrEqual(3, $r['score']);
    }

    public function test_seo_spam_with_url_yields_drop(): void
    {
        // score = SEO(-2) + URL(-3) + latin_only(-1) = -6, which is ≤ drop threshold(-5)
        // → label promoted from spam to drop (score-based drop, no hard-rule since email is valid)
        $fields = [
            'your-name'    => 'Melissa Johnson',
            'your-email'   => 'promo@example.com',
            'your-message' => 'Hi, we boost SEO positions, visit http://cheap-seo.net',
        ];
        $r = Classifier::classify($fields, ['reason' => 'Akismet']);
        self::assertSame('drop', $r['label']);
        self::assertLessThanOrEqual(-5, $r['score']);
    }

    public function test_honeypot_forces_spam_even_with_phone(): void
    {
        $fields = [
            'your-name'    => 'Анна',
            'your-tel'     => '+79031234567',
            'your-message' => 'сиделка для мамы',
        ];
        $r = Classifier::classify($fields, ['reason' => 'Honeypot']);
        self::assertSame('spam', $r['label']);
    }

    public function test_empty_fields_are_unclear(): void
    {
        $fields = [
            'your-email' => 'a@b.com',
        ];
        $r = Classifier::classify($fields, ['reason' => 'CF7 rules']);
        self::assertSame('unclear', $r['label']);
    }

    public function test_multiple_keywords_capped_at_minus_six(): void
    {
        $fields = [
            'your-message' => 'SEO, SEO, SEO, backlinks, crypto, casino, займ, bitcoin',
        ];
        $r = Classifier::classify($fields, ['reason' => 'Akismet']);
        // 8 hits × -2 would be -16; cap is -6
        self::assertGreaterThanOrEqual(-10, $r['score']); // keyword part >= -6, plus -3 for URL? none here
    }

    public function test_ru_domain_email_adds_one(): void
    {
        $fields = [
            'your-name'    => 'Иван',
            'your-email'   => 'ivan@yandex.ru',
            'your-message' => 'Здравствуйте, интересует услуга сиделки',
        ];
        $r = Classifier::classify($fields, ['reason' => 'Akismet']);
        $hasRuMail = false;
        foreach ($r['reasons'] as $reason) {
            if (strpos($reason['text'], 'ру-домен') !== false) {
                $hasRuMail = true;
            }
        }
        self::assertTrue($hasRuMail);
    }

    public function test_reasons_list_contains_sign_and_weight(): void
    {
        $fields = [
            'your-tel' => '+79031234567',
        ];
        $r = Classifier::classify($fields, ['reason' => 'Akismet']);
        self::assertNotEmpty($r['reasons']);
        self::assertArrayHasKey('sign', $r['reasons'][0]);
        self::assertArrayHasKey('weight', $r['reasons'][0]);
        self::assertArrayHasKey('text', $r['reasons'][0]);
    }

    public function test_latin_only_name_penalty(): void
    {
        $fields = [
            'your-name'    => 'John Smith',
            'your-message' => 'please help me with website ranking',
        ];
        $r = Classifier::classify($fields, ['reason' => 'Akismet']);
        $hasLatinPenalty = false;
        foreach ($r['reasons'] as $reason) {
            if ($reason['sign'] === '-' && strpos($reason['text'], 'латиница') !== false) {
                $hasLatinPenalty = true;
            }
        }
        self::assertTrue($hasLatinPenalty);
    }

    public function test_url_in_any_field_triggers_minus_three(): void
    {
        $fields = [
            'your-name'    => 'Ольга',
            'your-message' => 'посмотрите https://мойсайт.рф',
        ];
        $r = Classifier::classify($fields, ['reason' => 'Akismet']);
        $hasUrl = false;
        foreach ($r['reasons'] as $reason) {
            if (strpos($reason['text'], 'URL') !== false) {
                $hasUrl = true;
                self::assertSame('-', $reason['sign']);
                self::assertSame(3, $reason['weight']);
            }
        }
        self::assertTrue($hasUrl);
    }

    public function test_thresholds_client_edge(): void
    {
        // Score exactly 3 → client
        $fields = ['your-tel' => '+79031234567'];
        $r = Classifier::classify($fields, ['reason' => 'Akismet']);
        self::assertSame(3, $r['score']);
        self::assertSame('client', $r['label']);
    }

    public function test_thresholds_unclear_between_neg_one_and_two(): void
    {
        $fields = ['your-name' => 'Олег', 'your-message' => 'короткий'];
        $r = Classifier::classify($fields, ['reason' => 'Akismet']);
        self::assertGreaterThan(-2, $r['score']);
        self::assertLessThan(3, $r['score']);
        self::assertSame('unclear', $r['label']);
    }

    public function test_keyword_matching_case_insensitive(): void
    {
        $fields = ['your-message' => 'Продаём ВИАГРА с доставкой'];
        $r = Classifier::classify($fields, ['reason' => 'Akismet']);
        $matched = false;
        foreach ($r['reasons'] as $reason) {
            if (strpos($reason['text'], 'виагра') !== false) $matched = true;
        }
        self::assertTrue($matched);
    }

    public function test_detects_cyrillic_name_under_custom_field_key(): void
    {
        // Real form on washanyanya.ru uses keys like 'text-211' / 'text-212'
        // instead of 'your-name' / 'your-tel'. Classifier must still award
        // +1 for a cyrillic name via the value-based heuristic.
        $fields = [
            'text-211' => 'Александр',
            'text-212' => '+79776277470',
        ];
        $r = Classifier::classify($fields, ['reason' => 'Akismet']);
        $has_name = false;
        foreach ($r['reasons'] as $reason) {
            if (strpos($reason['text'], 'кириллическое имя') !== false) $has_name = true;
        }
        self::assertTrue($has_name, 'expected +1 кириллическое имя via value heuristic');
    }
}